pydantic_core._pydantic_core.ValidationError: 1 validation error for datetime Input should be a valid datetime [type=datetime_type, input_value=None, input_type=NoneType]

[R0boji]

Initial Checks

• I confirm that I'm using the latest version of Pydantic AI
• I confirm that I searched for my issue in https://github.com/pydantic/pydantic-ai/issues before opening this issue

Description

I realised that if model use tools, my script fails with that error.

File "D:\programming\\.venv\Lib\site-packages\pydantic_ai\agent.py", line 893, in run_sync
    return get_event_loop().run_until_complete(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\admin\AppData\Local\Programs\Python\Python312\Lib\asyncio\base_events.py", line 684, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "D:\programming\\.venv\Lib\site-packages\pydantic_ai\agent.py", line 494, in run
    async for _ in agent_run:
  File "D:\programming\\.venv\Lib\site-packages\pydantic_ai\agent.py", line 1985, in __anext__
    next_node = await self._graph_run.__anext__()
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\programming\\.venv\Lib\site-packages\pydantic_graph\graph.py", line 809, in __anext__
    return await self.next(self._next_node)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\programming\\.venv\Lib\site-packages\pydantic_graph\graph.py", line 782, in next
    self._next_node = await node.run(ctx)
                      ^^^^^^^^^^^^^^^^^^^
  File "D:\programming\\.venv\Lib\site-packages\pydantic_ai\_agent_graph.py", line 331, in run
    return await self._make_request(ctx)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\programming\\.venv\Lib\site-packages\pydantic_ai\_agent_graph.py", line 391, in _make_request
    model_response = await ctx.deps.model.request(message_history, model_settings, model_request_parameters)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\programming\\.venv\Lib\site-packages\pydantic_ai\models\openai.py", line 236, in request
    model_response = self._process_response(response)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\programming\\.venv\Lib\site-packages\pydantic_ai\models\openai.py", line 352, in _process_response
    timestamp = number_to_datetime(response.created)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\programming\\.venv\Lib\site-packages\pydantic_ai\_utils.py", line 327, in number_to_datetime
    return _datetime_ta.validate_python(x)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\programming\\.venv\Lib\site-packages\pydantic\type_adapter.py", line 421, in validate_python
    return self.validator.validate_python(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Example Code

from dotenv import load_dotenv
from pydantic_ai import Agent, RunContext
from pydantic_ai.models.openai import OpenAIModel
from pydantic_ai.providers.openrouter import OpenRouterProvider
import os
load_dotenv()
fast_model = OpenAIModel(
    "deepseek/deepseek-chat-v3-0324:free",
    provider=OpenRouterProvider(api_key=os.getenv("OPENROUTER_API_KEY"))
)
fast_agent = Agent(fast_model)
@fast_agent.tool_plain
def get_servers_status() -> list[dict]:
    """Get main servers' characteristics and resources, that are available to use."""
    return [
        {
            "id": 1,
            "location": "Berlin, Germany",
            "CPU": "AMD Ryzen 7800X3D",
            "CPU_FREQUENCY-GHZ": "3",
            "CPU_CORES": 16,
            "HDD-GB": 1024,
            "SSD-GB": 100,
            "RAM-MB": 20480,
            "RAM_TYPE": "DDR3"
        },
        {
            "id": 2,
            "location": "London, United Kingdom",
            "CPU": "Intel Pentium Gold",
            "CPU_FREQUENCY-GHZ": "1",
            "CPU_CORES": 2,
            "HDD-GB": 200,
            "SSD-GB": 5000,
            "RAM-MB": 40960,
            "RAM_TYPE": "DDR6"
        }
    ]
if __name__ == "__main__":
    print(fast_agent.run_sync("Give me servers' info").output)

Python, Pydantic AI & LLM client version

Python 3.12.1, Pydantic AI 0.4.3

[R0boji]

It worked once, but now it doesn't work anymore.

[R0boji]

print(fast_agent.run_sync("Give me servers' info").output) Python indicates this line.

[R0boji]

I added print(response) in D:\programming\.venv\Lib\site-packages\pydantic_ai\models\openai.py, it returns ChatCompletion(id=None, choices=None, created=None, model=None, object=None, service_tier=None, system_fingerprint=None, usage=None, error={'message': 'Internal Server Error', 'code': 500}, user_id='user_2vG8JHNDDYbHoK4GuFqOWMKUs0f')

[DouweM]

@R0boji So it looks like we sometimes get created=None, which is easy enough to work around as we did here:

pydantic-ai/pydantic_ai_slim/pydantic_ai/models/huggingface.py

Lines 235 to 238 in 0b3bf86

	if response.created:
	timestamp = datetime.fromtimestamp(response.created, tz=timezone.utc)
	else:
	timestamp = _now_utc()

Can you please file a PR to add that check? Note that we still need number_to_datetime, not datetime.fromtimestamp in this case.

The Internal Server Error is not something we can do much about, unfortunately, that's all on OpenRouter's side.

[R0boji]

What's interesting is that OpenRouter official documentation doesn't explain what code 500 means, although it explains codes like 502 and 503 🫠

[R0boji]

@DouweM Ok, see #2247